CN110345955A - Perception and planning cooperation frame for automatic Pilot - Google Patents
Perception and planning cooperation frame for automatic Pilot Download PDFInfo
- Publication number
- CN110345955A CN110345955A CN201910034390.7A CN201910034390A CN110345955A CN 110345955 A CN110345955 A CN 110345955A CN 201910034390 A CN201910034390 A CN 201910034390A CN 110345955 A CN110345955 A CN 110345955A
- Authority
- CN
- China
- Prior art keywords
- key area
- automatic driving
- driving vehicle
- perception information
- perception
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 230000008447 perception Effects 0.000 title claims abstract description 103
- 238000000034 method Methods 0.000 claims abstract description 53
- 238000012545 processing Methods 0.000 claims description 31
- 230000015654 memory Effects 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 16
- 230000006399 behavior Effects 0.000 claims 1
- 238000003860 storage Methods 0.000 description 35
- 238000004891 communication Methods 0.000 description 16
- 230000001149 cognitive effect Effects 0.000 description 12
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 7
- 238000013507 mapping Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000001133 acceleration Effects 0.000 description 5
- 230000004888 barrier function Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 5
- 238000007405 data analysis Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 2
- 238000013479 data entry Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000010354 integration Effects 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000014759 maintenance of location Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 241000630329 Scomberesox saurus saurus Species 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000005452 bending Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 230000010267 cellular communication Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012517 data analytics Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003203 everyday effect Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 229910044991 metal oxide Inorganic materials 0.000 description 1
- 150000004706 metal oxides Chemical class 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000005036 potential barrier Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0015—Planning or execution of driving tasks specially adapted for safety
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0268—Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/10—Number of lanes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2554/00—Input parameters relating to objects
- B60W2554/40—Dynamic objects, e.g. animals, windblown objects
- B60W2554/402—Type
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Aviation & Aerospace Engineering (AREA)
- Mechanical Engineering (AREA)
- Transportation (AREA)
- Human Computer Interaction (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Game Theory and Decision Science (AREA)
- Medical Informatics (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
Sensing module is configured to based on the driving environment around sensing data perception automatic driving vehicle (ADV), and generates perception information using various sensor models or method.Perception information describes the driving environment perceived.Based on perception information, planning module is configured to representation of plan for the route of current planning horizon or the track in path.Then, based on the TRAJECTORY CONTROL and driving ADV.In addition, planning module is according to ADV when prelocalization or position determine based on track the key area (also referred to as key area) around ADV.The metadata of description key area is transmitted to sensing module via application programming interface (API), to allow perception information of the sensing module according to key area generation for next planning horizon.
Description
Technical field
Embodiment of the present disclosure relates in general to operation automatic driving vehicle.More specifically, embodiment of the present disclosure relates to
And the perception and planning of automatic Pilot.
Background technique
Occupant, especially driver can be driven from some with the vehicle of automatic driving mode operation (for example, unmanned)
It sails and is freed in relevant responsibility.When being run with automatic driving mode, it is each that onboard sensor can be used to navigate to for vehicle
Position, thus allow vehicle in the case where minimum human-computer interaction or no any passenger some cases downward driving.
Automatic Pilot is a kind of technology of complexity, is related to multiple modules, including high definition map, positioning, perception, prediction, rule
It draws, the modules such as control.In the art, interface is defined for each of module, and each module executes their own
Work.Information between module is unilateral or unidirectional.However, complex environment and calculating limitation so that individual module can not be
Drive or calculate in planning horizon all the elements.Therefore, module needs effectively to exchange information and uses computing resource.Automatically it drives
It sails and lacks cooperation between module.
Summary of the invention
In the one side of the disclosure, a kind of for operating the method implemented by computer of automatic driving vehicle, packet is provided
It includes:
Based on sensing data obtained from multiple sensors, driving around automatic driving vehicle is perceived by sensing module
Environment is sailed, generates perception information using multiple sensor models;
Based on from the received perception information of the sensing module, current drive cycle is used for by planning module planning
Track;
Work as prelocalization according to the automatic driving vehicle, is based on the track, determines around the automatic driving vehicle
Key area;
The automatic driving vehicle is controlled to be travelled according to the track;And
The metadata for describing the key area is transmitted to the sensing module via application programming interface, to permit
Perhaps the described sensing module is generated according to the key area of the automatic driving vehicle to be believed for the perception of next drive cycle
Breath.
In another aspect of the present disclosure, a kind of non-transitory machine readable media for being stored with instruction, the finger are provided
Order causes the processor to execute operation when executed by the processor, and the operation includes:
Based on sensing data obtained from multiple sensors, driving around automatic driving vehicle is perceived by sensing module
Environment is sailed, generates perception information using multiple sensor models;
Based on from the received perception information of the sensing module, current drive cycle is used for by planning module planning
Track;
Work as prelocalization according to the automatic driving vehicle, is based on the track, determines around the automatic driving vehicle
Key area;
The automatic driving vehicle is controlled to be travelled according to the track;And
The metadata for describing the key area is transmitted to the sensing module via application programming interface, to permit
Perhaps the described sensing module is generated according to the key area of the automatic driving vehicle to be believed for the perception of next drive cycle
Breath.
In the disclosure in another aspect, providing a kind of data processing system, comprising:
Processor;And
Memory is attached to the processor;And
Sensing module and planning module, load execute in the memory and by the processor to execute operation, institute
Stating operation includes:
Based on sensing data obtained from multiple sensors, perceived around automatic driving vehicle by the sensing module
Driving environment, using multiple sensor models generate perception information,
Based on from the received perception information of the sensing module, driven by planning module planning for current
The track in period,
Work as prelocalization according to the automatic driving vehicle, is based on the track, determines around the automatic driving vehicle
Key area,
The automatic driving vehicle is controlled to be travelled according to the track;And
The metadata for describing the key area is transmitted to the sensing module via application programming interface, to permit
Perhaps the described sensing module is generated according to the key area of the automatic driving vehicle to be believed for the perception of next drive cycle
Breath.
Detailed description of the invention
Embodiment of the present disclosure is shown in each figure of attached drawing in mode for example and not limitation, the identical ginseng in attached drawing
Examine label instruction similar components.
Fig. 1 is the block diagram for showing networked system according to one embodiment.
Fig. 2 is the exemplary block diagram for showing automatic driving vehicle according to one embodiment.
Fig. 3 A to Fig. 3 B is the perception and planning that are used together with automatic driving vehicle shown according to one embodiment
The exemplary block diagram of system.
Fig. 4 is the exemplary block diagram for showing planning module according to one embodiment.
Fig. 5 A to Fig. 5 C shows the key area for different Driving Scenes according to certain embodiments.
Fig. 6 shows the example of the data structure for storing key area information according to one embodiment.
Fig. 7 is the flow chart for showing the process of operation automatic driving vehicle according to one embodiment.
Fig. 8 is the block diagram for showing data processing system according to one embodiment.
Specific embodiment
The various embodiments and aspect of the disclosure will be described with reference to details as discussed below, attached drawing will show described
Various embodiments.Following description and attached drawing are the explanation of the disclosure, and are not construed as limiting the disclosure.Description
Many specific details are to provide the comprehensive understanding to the various embodiments of the disclosure.However, in some cases, not retouching
Well-known or conventional details is stated, to provide the succinct discussion to embodiment of the present disclosure.
Referring to for " embodiment " or " embodiment " is meaned that the embodiment is combined to be retouched in this specification
The a particular feature, structure, or characteristic stated may include at least one embodiment of the disclosure.Phrase is " in an embodiment
In " appearance in each in the present specification place need not all refer to same embodiment.
According to some embodiments, help to perceive the meter for more efficiently using them with planning cooperation frame using perception
Calculate resource.Sensing module was configured to based on sensing data perception automatic driving vehicle (ADV) week obtained from various sensors
The driving environment enclosed, and perception information is generated using various sensor models or method.Perception information describes the driving perceived
Environment.Based on perception information, planning module is configured to road of the representation of plan for current planning horizon (also referred to as drive cycle)
The track in line or path.Then, based on the TRAJECTORY CONTROL and driving ADV.In addition, planning module according to ADV when prelocalization or
Position determines the key area (also referred to as key area) around ADV based on track.The metadata of key area is described via answering
It is transmitted to sensing module with Program Interfaces (API), to allow sensing module to generate according to key area for next planning
The perception information in period.
In one embodiment, key area may include that ADV may potentially interfere with it during next planning horizon
Its traffic or other traffic may potentially interfere with one or more regions of ADV.Believe generating the perception for next period
When breath, sensing module generates the first perception information of perception key area using the first sensor model or method.Sensing module makes
With remaining second perception information of Area generation that the second sensor model or method are in addition to key area.First sensor model can
For generating the perception information with higher precision or resolution ratio based on 3D sensing data, this need more processing resource and/
Or the longer time completes.Second sensor model, which can be used for generating based on 2D sensing data, has lower accuracy or resolution ratio
Perception information, this needs less process resource and/or shorter time to complete.
In one embodiment, when determining key area, planning module is based on the track of ADV and when prelocalization determines
The Driving Scene of ADV.Search operation is executed in the database based on Driving Scene, to be described or be limited and Driving Scene phase
The metadata or definition of corresponding key area.For example, metadata may include illustrating for limiting, determining or calculating key
The method in area or the information of rule.Database can be the Driving Scene with multiple map entries to key area and (drive
Scene/key area) mapping table.Specific Driving Scene is mapped to the first number for limiting specific key area by each map entry
According to.Based on metadata, according to one embodiment, polygon is determined to indicate key area.The shape of polygon can be based on member
Data are determined, while the size of polygon can be determined based on following: track (for example, ADV when prelocalization, speed,
Direction of advance), the physical characteristic (for example, physical size or dimension of ADV) of ADV, and/or the current sense provided by sensing module
Know information (for example, lane configurations).Then, it is determined that the coordinate of polygon vertex.The coordinate of polygon vertex is for indicating crucial
Area.Then, the vertex of polygon is fed back into sensing module, is used with allowing sensing module to generate using different cognitive methods
In the perception information of next planning horizon.
Fig. 1 is the block diagram for showing automatic driving vehicle network configuration in accordance with one embodiment of the present disclosure.With reference to figure
1, network configuration 100 includes the automatic Pilot that one or more servers 103 to 104 can be communicably coupled to by network 102
Vehicle 101.Although showing an automatic driving vehicle, multiple automatic driving vehicles can be connected to by network 102 each other and/
Or it is connected to server 103 to 104.Network 102 can be any kind of network, for example, wired or wireless local area network
(LAN), the wide area network (WAN) of such as internet, cellular network, satellite network or combinations thereof.Server 103 to 104 can be
Any kind of server or cluster of servers, such as, network or Cloud Server, application server, back-end server or its group
It closes.Server 103 to 104 can be data analytics server, content server, traffic information server, map and point of interest
(MPOI) server or location server etc..
Automatic driving vehicle refers to the vehicle that can be configured under automatic driving mode, in the automatic driving mode
Lower vehicle navigates in the case where few or input not from driver passes through environment.This automatic driving vehicle may include
Sensing system, the sensing system have the one or more for being configured to detect information related with vehicle running environment
Sensor.The vehicle and its associated controller are navigated using information detected through the environment.Automatic Pilot
Vehicle 101 can be run in a manual mode, under full-automatic driving mode or under the automatic driving mode of part.
In one embodiment, automatic driving vehicle 101 includes, but are not limited to perception and planning system 110, vehicle
Control system 111, wireless communication system 112, user interface system 113 and sensing system 115.Automatic driving vehicle 101 is also
It may include the certain common components for including in common vehicle: engine, wheel, steering wheel, speed changer etc., the component
It can be controlled with planning system 110 using a variety of signals of communication and/or order by vehicle control system 111 and/or perception, it should
A variety of signals of communication and/or order are for example, acceleration signals or order, reduce-speed sign or order, turn signal or order, braking letter
Number or order etc..
Component 110 to 115 can be communicably coupled to each other via interconnection piece, bus, network or combinations thereof.For example, component
110 to 115 can be connected to each other via controller LAN (CAN) bus communication.CAN bus is configured to allow micro-control
Device and device processed in the application of not host with the vehicle bus standard that communicates with one another.It is initially multiplexing in automobile
The message based agreement of electric wiring design, but it is also used for many other environment.
Referring now to Figure 2, in one embodiment, sensing system 115 includes but is not limited to one or more camera shootings
Machine 211, global positioning system (GPS) unit 212, Inertial Measurement Unit (IMU) 213, radar cell 214 and optical detection and survey
Away from (LIDAR) unit 215.GPS unit 212 may include transceiver, and the transceiver can be operated to provide about automatic Pilot vehicle
Position information.IMU unit 213 can sense position and the change in orientation of automatic driving vehicle based on inertial acceleration.
The system that radar cell 214 can indicate to sense the object in the home environment of automatic driving vehicle using radio signal.?
In some embodiments, in addition to sensing object, in addition radar cell 214 can sense the speed and/or direction of advance of object.
Laser can be used to sense the object in automatic driving vehicle local environment in LIDAR unit 215.In addition to other system units,
LIDAR unit 215 may also include one or more laser sources, laser scanner and one or more detectors.Video camera 211
It may include one or more devices for acquiring the image of automatic driving vehicle ambient enviroment.Video camera 211 can be still life
Video camera and/or video camera.Video camera, which can be, mechanically to be moved, for example, by the way that video camera is mounted on rotation
And/or on sloping platform.
Sensing system 115 may also include other sensors, such as: sonar sensor, turns to sensing at infrared sensor
Device, throttle sensor, braking sensor and audio sensor (for example, microphone).Audio sensor can be configured to from certainly
Sound is acquired in the dynamic environment for driving vehicle periphery.Rotation direction sensor can be configured to sensing steering wheel, vehicle wheel or its
Combined steering angle.Throttle sensor and braking sensor sense the throttle position and application position of vehicle respectively.Some
Under situation, throttle sensor and braking sensor can be integrated into integrated form throttle/braking sensor.
In one embodiment, vehicle control system 111 includes but is not limited to steering unit 201, throttle unit 202
(also referred to as accelerator module) and brake unit 203.Steering unit 201 is used to adjust direction or the direction of advance of vehicle.Throttle
Unit 202 is used to control the speed of motor or engine, the speed of motor or engine so that control vehicle speed and
Acceleration.Brake unit 203 makes the wheel of vehicle or tire deceleration make vehicle deceleration by providing friction.It should be noted that such as Fig. 2
Shown in component can be implemented with hardware, software, or its combination.
Referring back to Fig. 1, wireless communication system 112 allows automatic driving vehicle 101 and such as device, sensor, other
Communication between the external systems such as vehicle.For example, wireless communication system 112 can be with the direct channel radio of one or more devices
Letter, or carried out wireless communication via communication network, such as, communicated by network 102 with server 103 to 104.Wireless communication
Any cellular communications networks or WLAN (WLAN) can be used in system 112, for example, using WiFi, with another component or
System communication.Wireless communication system 112 can such as using infrared link, bluetooth with device (for example, the mobile device of passenger,
Loudspeaker in display device, vehicle 101) direct communication.User interface system 113 can be implement in vehicle 101 it is outer
The part of device is enclosed, including such as keyboard, touch panel display device, microphone and loudspeaker.
Some or all of function of automatic driving vehicle 101 can be controlled or be managed with planning system 110 by perception, especially
It under automatic driving mode when operating.Perception includes necessary hardware (for example, processor, storage with planning system 110
Device, storage device) and software (for example, operating system, planning and Vehicle routing program), to be from sensing system 115, control
System 111, wireless communication system 112 and/or user interface system 113 receive information, and the received information of processing institute is planned from starting
Route or path of the point to destination, then drive vehicle 101 based on planning and controlling information.Alternatively, perception with
Planning system 110 can be integrated with vehicle control system 111.
For example, the initial position and destination of stroke can be for example specified via user interface as the user of passenger.Sense
Know and obtains stroke related data with planning system 110.For example, perception can obtain position from MPOI server with planning system 110
It sets and route information, the MPOI server can be a part of server 103 to 104.Location server provides position clothes
Business, and MPOI server provides the POI of Map Services and certain positions.Alternatively, such position and MPOI information can this
Ground cache is in the permanent storage device of perception and planning system 110.
When automatic driving vehicle 101 is moved along route, perception and planning system 110 can also from traffic information system or
Server (TIS) obtains Real-time Traffic Information.It should be noted that server 103 to 104 can be operated by third party entity.It can replace
The function of Dai Di, server 103 to 104 can be integrated with perception with planning system 110.Based on Real-time Traffic Information,
MPOI information and location information and the real-time home environment data for being detected or being sensed by sensing system 115 are (for example, obstacle
Object, object, neighbouring vehicle), perception with planning system 110 can plan best route and according to the route planned for example via
Control system 111 drives vehicle 101, with safety and efficiently reaches specified destination.
Server 103 can be data analysis system, to execute data analysis service for various clients.Implement at one
In mode, data analysis system 103 includes data collector 121 and machine learning engine 122.Data collector 121 is from various
Vehicle (automatic driving vehicle or the conventional vehicles driven by human driver), which is collected, drives statistical data 123.Drive statistical number
According to 123 include indicate issued steering instructions (for example, throttle, braking, steering order) and by vehicle sensor not
The information of the response (for example, speed, acceleration, deceleration, direction) for the vehicle that same time point captures.Drive statistical data 123
It may also include the information of the driving environment under description different time points, for example, route (including initial position and destination locations),
MPOI, condition of road surface, weather conditions etc..
Based on statistical data 123 is driven, for various purposes, machine learning engine 122 generates or one group of rule of training, calculation
Method and/or prediction model 124.For example, data 123 may include limiting the information of various Driving Scenes.For each Driving Scene,
Data 123 may also include metadata or algorithm, in the key for determining ADV in the case where working as prelocalization or position of given ADV
Area.In one embodiment, Driving Scene/key area mapping table is produced.It then, can be by Driving Scene/crucially
Area's mapping table uploads in ADV to determine the key area driven in real time.
Fig. 3 A and Fig. 3 B are the perception and planning that are used together with automatic driving vehicle shown according to one embodiment
The exemplary block diagram of system.System 300 can be implemented as a part of the automatic driving vehicle 101 of Fig. 1, including but not limited to feel
Know and planning system 110, control system 111 and sensing system 115.With reference to Fig. 3 A to Fig. 3 B, perception is wrapped with planning system 110
Include but be not limited to locating module 301, sensing module 302, prediction module 303, decision-making module 304, planning module 305, control mould
Block 306 and Vehicle routing module 307.
Some or all of module 301 to 307 can be implemented with software, hardware or combinations thereof.For example, these modules can
It is mounted in permanent storage device 352, is loaded into memory 351, and held by one or more processors (not shown)
Row.It should be noted that some or all of these modules are communicably connected to some or complete of the vehicle control system 111 of Fig. 2
Portion's module or it is integrated together.Some in module 301 to 307 can be integrated into integration module together.
The determining automatic driving vehicle 300 of locating module 301 works as prelocalization (for example, utilizing GPS unit 212) and management
Any data relevant to the stroke of user or route.(also known as the map and route module) management of locating module 301 and use
The relevant any data of the stroke or route at family.User can for example log in via user interface and the initial position of specified stroke
The destination and.Other component communications of such as map and route information 311 of locating module 301 and automatic driving vehicle 300, with
Obtain stroke related data.For example, locating module 301 can obtain position from location server and map and POI (MPOI) server
It sets and route information.Location server provides location-based service, and MPOI server provides Map Services and certain positions
POI, so as to a part of cache as map and route information 311.When automatic driving vehicle 300 is moved along route
When, locating module 301 can also obtain Real-time Traffic Information from traffic information system or server.
Based on the sensing data provided by sensing system 115 and the location information obtained by locating module 301, perception
Module 302 determines the perception to ambient enviroment.Perception information can indicate everyday driver in the vehicle periphery of driver skipper
The thing that will be perceived.Perception may include for example, by using object form lane configurations (for example, rectilinear stretch or bending lane),
Traffic light signals, the relative position of another vehicle, pedestrian, building, crossing or other traffic correlating markings are (for example, stop
Only mark, yield signs) etc..
Sensing module 302 may include the function of computer vision system or computer vision system, with handle and analyze by
The image of one or more video camera acquisitions, to identify the object and/or feature in automatic driving vehicle environment.The object
It may include traffic signals, road boundary, other vehicles, pedestrian and/or barrier etc..Object can be used to know for computer vision system
Other algorithm, video tracking and other computer vision techniques.In some embodiments, computer vision system can draw ring
Condition figure, tracking object, and the speed etc. of estimation object.Sensing module 302 may be based on by such as radar and/or LIDAR
Other sensors provide other sensing datas carry out test object.
For each object, prediction module 303 predicts how object will show in this case.Prediction is based on perception
What data executed, which perceives at the time point for considering chart portfolio/route information 311 and traffic rules 312 and drives
Environment.For example, if object is the vehicle in opposite direction and current driving environment includes crossroad, prediction module 303
Whether prediction vehicle may be moved forward or be turned straight.If perception data shows that crossroad does not have traffic lights,
Prediction module 303 may predict that vehicle may need parking completely before entering the intersection.If perception data shows
Vehicle is currently in unique lane or unique lane of turning right, then prediction module 303 may predict that vehicle will be more likely to distinguish
Turn left or turns right.
For each object, decision-making module 304 makes disposing the decision of object.For example, being directed to special object
The metadata (for example, speed, direction, angle of turn) of (for example, another vehicle in intersecting routes) and description object, decision
Module 304 determines how with the object to meet (for example, overtake other vehicles, give way, stop, be more than).Decision-making module 304 can be according to such as
Traffic rules drive the rule set of rule 312 to make such decision, and the rule set is storable in permanent storage device
In 352.
Vehicle routing module 307 is configured to provide one or more routes or path from starting point to destination.It is right
In the given stroke from initial position to destination locations, such as from the received given stroke of user, Vehicle routing module 307 is obtained
Route and cartographic information 311 are obtained, and is determined from initial position to all potential routes or path for arriving at the destination position.Route
The module 307 is arranged to produce the reference line of topographic map form, it is determined that from initial position to arriving at the destination each of position
Route.Reference line refers to the not ideal way of any interference by other such as other vehicles, barrier or traffic condition or road
Diameter.That is, ADV should accurately or closely follow reference line if not having other vehicles, pedestrian or barrier on road.So
Afterwards, topographic map is provided to decision-making module 304 and/or planning module 305.Decision-making module 304 and/or planning module 305 check
All possible route, to select and change one in best route according to the other data provided by other modules, wherein
The all traffic conditions for example from locating module 301 of other data, the driving environment perceived by sensing module 302 and by pre-
Survey the traffic condition that module 303 is predicted.According to the specific driving environment under time point, for controlling Actual path or the road of ADV
Line is possibly close to or the reference line different from being provided by Vehicle routing module 307.
Based on for decision in each of perceived object, 305 use of planning module is by Vehicle routing module 307
It is automatic driving vehicle planning path or route and drive parameter (for example, distance, speed based on the reference line of offer
And/or angle of turn).In other words, for given object, what the decision of decision-making module 304 does to the object, and planning module
305 determine how and do.For example, decision-making module 304 can determine to be more than the object, and planning module for given object
305 can determine that still right side is more than in the left side of the object.Planning and control data are generated by planning module 305, including are retouched
State the information how vehicle 300 will move in next mobile circulation (for example, next lines/paths section).For example, planning and control
Data processed can indicate that vehicle 300 is 10 meters mobile with 30 mph. (mph) of speed, then change to the right side with the speed of 25mph
Side lane.
Based on planning and control data, control module 306 are led to according to by planning and controlling route that data limit or path
It crosses and sends vehicle control system 111 for order appropriate or signal to control and drive automatic driving vehicle.It is described planning and
Control data bag includes enough information, is arranged or is driven using vehicle appropriate to put in different times along path or route
Parameter (for example, throttle, braking and turning command) is driven to second point for first point of vehicle from route or path.
In one embodiment, the planning stage executes in multiple planning horizons (being also referred to as used as command cycle), for example,
It is executed in the period that each time interval is 100 milliseconds (ms).For each of planning horizon or command cycle, by base
One or more control commands are issued in planning and controlling data.That is, planning module 305 plans next road for every 100ms
Line segment or route segment, it may for example comprise target position and ADV reach the time required for target position.Alternatively, planning module
305 may also dictate that specific speed, direction and/or steering angle etc..In one embodiment, planning module 305 is next
Predetermined period (such as, 5 seconds) programme path section or route segment.For each planning horizon or drive cycle, 305 base of planning module
The target position of current period (for example, next 5 seconds) is used in the target position planning planned in previous cycle.Control mould
Block 306 is then based on the planning of current period and control data generate one or more control commands (for example, throttle, braking, turning
To control command).
It should be noted that decision-making module 304 and planning module 305 can be integrated into integration module.304/ planning module of decision-making module
305 may include the function of navigation system or navigation system, to determine the driving path of automatic driving vehicle.For example, navigation system
Can determine a series of speed and direction of advance moved for realizing automatic driving vehicle along following path: the path makes
While automatic driving vehicle advances along the path based on driveway for leading to final destination, substantially avoid perceiving
Barrier.Destination can be set according to the user's input carried out via user interface system 113.Navigation system can drive automatically
It sails while vehicle is currently running and dynamically updates driving path.Navigation system can will come from GPS system and one or more ground
The data of figure merge, to determine the driving path for being used for automatic driving vehicle.
304/ planning module 305 of decision-making module may also include the function of anti-collision system or anti-collision system, to identificate and evaluate simultaneously
And avoid or cross in other ways the potential barrier in the environment of automatic driving vehicle.For example, anti-collision system can by with
Under type realizes the variation in the navigation of automatic driving vehicle: one or more subsystems in operation control system 111 are adopted
Take deflecting manipulation, turn control, braking maneuver etc..Anti-collision system can travel pattern, condition of road surface based on surrounding etc. it is automatic really
Fixed feasible obstacle avoidance manipulation.Anti-collision system, which may be configured such that, automatically drives when other sensor system senses to being located at
Deflecting is not taken to manipulate whens sailing vehicle for vehicle, architectural barriers object etc. in adjacent area that deflecting enters.Anti-collision system can be certainly
Dynamic selection not only can be used but also the safety of automatic driving vehicle occupant maximumlly manipulated.Prediction, which may be selected, in anti-collision system makes
Obtain the evacuation manipulation for occurring the acceleration of minimum in the passenger compartment of automatic driving vehicle.
According to one embodiment, sensing module 302 is based on sensing data and perceives driving environment, and uses various perception
Method or model 313 generate perception information.Some in cognitive method or model for handling sensing data can be related to compared with
Multiprocessing resource and long period, such as processing 3D LIDAR data, to generate the perception information of higher precision and resolution ratio, and
Other cognitive methods or model can be related to less process resource and short period, to generate the perception letter of lower accuracy and resolution ratio
Breath.In view of physical planning/drive cycle finite time is (for example, 100ms to 200ms), most conventional automatic Pilot system
System selection meets limited planning time using the cognitive method of low resolution.However, the perception data of higher resolution
Better driving environment visibility will be provided for planning module 305, it is potential to avoid to plan better route or path
Collision, but it is also required to more process resources and time.
In one embodiment, with reference to Fig. 3 A and Fig. 3 B, when planned trajectory, planning module 305 is configured in addition to life
Except the track for controlling ADV of current planning horizon, the key area around ADV is also determined.It then, will be about key
The information 320 in area feeds back to sensing module 302.Based on key area, sensing module 302 may be selected different cognitive method or
Model 313 is come the region (referred to as non-key area) that handles key area and in addition to key area, with all for next planning
Phase.Specifically, for example, sensing module 302 generates key area using the cognitive method or model of higher precision and resolution ratio
Perception information, while generating using the cognitive method or model of lower accuracy and resolution ratio the perception information in other regions.
Higher precision and resolution ratio are generated although more processing resource and long period may be spent for key area
Perception information, but for safety purposes, it can be for key area adjustment in this way.In most of time, for removing
Region (for example, more far region) except key area, planning module 305 does not need high-resolution perception information.Due to closing
Key area is relatively small compared with remaining region part, therefore additional processing resources and time can be limited to still meet planning week
The amount of management of phase time requirement.For example, sensing module 302 can generate the perception letter of key area using 3D LIDAR data
It ceases, while generating the perception information of non-critical areas using 2D LIDAR data.It is commonly used for processing 3D LIDAR data
Resource and time are higher than resource and the time of processing 2D LIDAR data.By providing back key area information to sensing module
302, sensing module 302 can be used the combination of different cognitive method/models 313 with mixed mode operations, to handle not same district
Domain, while it still meets the finite time requirement of planning horizon.
Fig. 4 is the exemplary block diagram for showing planning module according to one embodiment.With reference to Fig. 4, planning module 305,
Among other things, including scene determining module 401 and key area determining module 402.According to one embodiment, in determination
When key area, scene determining module 401 is configured to based on the track of ADV and when prelocalization determines the driver training ground under the time point
Scape.Driving Scene can be the scene of straight line driving, left-hand rotation or right-hand rotation, u turn or lane change etc..Driving Scene can be based on
The information of the track generated by planning module 305 determines, for example, at the different time points on track, the song of the track of ADV
Line and speed and direction of advance.
Based on Driving Scene, key area determining module 402 is configured to determine the key area of above-mentioned specific Driving Scene.
Different Driving Scenes can be associated with the different shape of key area or size.In one embodiment, planning module 305
Database is maintained, the key area of the various Driving Scenes of the database purchase defines information.It, can be to number based on specific Driving Scene
It issues and searches for according to library, to search for the information for the key area for limiting given Driving Scene.In one embodiment, this data
Implementable library is Driving Scene/key area mapping table 314 a part.
As shown in Figure 4, Driving Scene/key area mapping table 314 includes multiple map entries.Each map entry is equal
Driving Scene 411 is mapped to description or limits the metadata or definition of key area corresponding with Driving Scene.At one
In embodiment, the metadata of key area may include one group of rule or algorithm, with the driving environment based on the time point come really
Fixed or calculating key area.No due to each driving environment (for example, lane configurations and size, vehicle physical size and limitation etc.)
Together, therefore at least the size of key area must be dynamically determined, for example, being based on track.In one embodiment, based on driving
Sail scene, key area determining module 402 executes search operation in Driving Scene/key area mapping table 314, with positioning with
The matched map entry of Driving Scene.Then the metadata that key area defines 412 is obtained from the entry to match.Then,
Key area is calculated using the key area algorithm or method that obtain from metadata.
Fig. 5 A shows the example of the key area of the Driving Scene driven for straight line.In this example, ADV is on lane
Straight line drives.Therefore, the key area in the scene will include the left and right in region and adjacent lane before ADV close to area
Domain, because the traffic in these regions may potentially influence the driving of ADV, vice versa.Fig. 5 B is shown for crossroad
The example of the key area of the right-hand bend Driving Scene at place.In this example, ADV attempts to turn right, therefore key area Jiang Bao
Include the opposing traffic in opposite direction and crisscross region from left to right.Fig. 5 C shows the left-hand rotation at for crossroad
The example of the key area of change or u turn Driving Scene.In this example, key area includes the zone similarity of Fig. 5 B.This
Outside, key area includes the region for influencing intersection traffic from right to left.
Then, the information for describing key area is transmitted back to sensing module 302, to allow sensing module 302 for key
Regional and non-key area handles sensing data using different cognitive method or model.According to one embodiment, when
When transmitting the information about key area, specific data structure is defined and is used to store key area information.
Fig. 6 is the example for showing the data structure for storing the feedback information for perception according to one embodiment
Block diagram.With reference to Fig. 6, data structure 600 includes multiple data members 601 to 605.The storage of header 601 indicate corresponding track and
The timestamp of key area determined time.602 storage track of path length or the length in path are (for example, with meter Wei Dan
Position).Path time 603 stores ADV and completes track for the time spent (for example, in seconds).Track lattice array 604 includes
Data entry array is constituted information in each of the tracing point of track with storage.The tracing point information of each tracing point is at least
The direction of advance (θ) of coordinate (x, y, z), tracing point including tracing point and ADV from currently navigate to from the tracing point when
Between (t).Key area lattice array 605 includes data entry array, in the form of the vertex of area definition key area, polygon
Point coordinate (x, y).Key point refers to that the turning point of the polygon as shown in Fig. 5 A to Fig. 5 B (is expressed as the roundlet of turning angle
Circle).
Once sensing module 302 receives data structure, sensing module 302 can parse data structure, to be based on track
Point 604 and key area point 605 determine key area and non-key area.Then, sensing module can be to different sensors data
(for example, 2D LIDAR data from 3D LIDAR data) applies different cognitive methods or model, all for next planning to generate
The perception information of the key area of phase and non-key area.Therefore, it optimizes the quality of perception information and generates perception information
Required processing time and resource.
Fig. 7 be show according to embodiment of the present invention for operate automatic driving vehicle process it is exemplary
Flow chart.Process 700 can be executed by processing logic, and the processing logic may include software, hardware or their combination.For example,
Process 700 can be executed by sensing module 302 and/or planning module 305.With reference to Fig. 7, in operation 701, sensing module be based on from
Sensing data that various sensors (for example, LIDAR, RADAR, video camera) obtain perceives the driving environment around ADV.Make
Perception information is generated with various cognitive methods and model.In operation 702, planning module is based on from the received perception of sensing module
Information carrys out representation of plan for the path of current planning horizon or the track of route.In operation 703, according to the current fixed of ADV
Position, the key area around ADV is determined based on track.In operation 704, then according to TRAJECTORY CONTROL and driving ADV.In addition,
In operation 705, the information about key area is then transmitted to sensing module, to allow sensing module according to key area
The perception information for next planning horizon is generated using different cognitive method or model with non-key area.
It should be noted that some or all of component being such as shown and described above can be real in software, hardware or combinations thereof
It applies.For example, the implementable software to be fixed and stored in permanent storage device of this base part, the software can pass through processing
The load of device (not shown) is executed in memory and in memory to implement through process described herein or operation.It can replace
Dai Di, this base part it is implementable for programming or be embedded into specialized hardware (such as, integrated circuit (for example, specific integrated circuit or
ASIC), digital signal processor (DSP) or field programmable gate array (FPGA)) in executable code, the executable generation
Code can be accessed via the respective drive program and/or operating system of carrying out self-application.In addition, it is processor that this base part is implementable
Or the specific hardware logic in processor cores, as the instruction that can pass through one or more specific instruction access by software component
A part of collection.
Fig. 8 is the exemplary block diagram for showing the data processing system that can be used together with an embodiment of the disclosure.
For example, system 1500 can indicate any data processing system of any of the above-described execution above process or method,
For example, any of the perception of Fig. 1 and planning system 110 or server 103 to 104.System 1500 may include it is many not
Same component.These components it is implementable for integrated circuit (IC), the part of integrated circuit, discrete electronics or be suitable for circuit
Other modules of plate (such as, the mainboard of computer system or insertion card) are embodied as being incorporated to computer system in other ways
Rack in component.
It shall yet further be noted that system 1500 is intended to show that the multipart high-order view perhaps of computer system.It is, however, to be understood that
, can have additional component in some embodiments, in addition, can have the different arrangements of shown component in other embodiments.
System 1500 can indicate desktop computer, laptop computer, tablet computer, server, mobile phone, media player,
Personal digital assistant (PDA), smartwatch, personal communicator, game device, network router or hub, wireless access point
(AP) or repeater, set-top box or combinations thereof.Although in addition, illustrate only individual machine or system, term " machine " or
It is described herein to execute that " system " should also be understood as including either individually or collectively one (or multiple) instruction set of execution
Any one or more of method machine or system any set.
In one embodiment, system 1500 includes the processor 1501 connected by bus or interconnection piece 1510, deposits
Reservoir 1503 and device 1505 to 1508.Processor 1501 can be indicated including single processor kernel or multiple processors
The single processor of kernel or multiple processors.Processor 1501 can indicate one or more general processors, such as, micro process
Device, central processing unit (CPU) etc..More specifically, processor 1501 can be complex instruction set calculation (CISC) microprocessor,
Reduced instruction set computing (RISC) microprocessor, very long instruction word (VLIW) microprocessor or the processing for implementing other instruction set
Device or the processor for implementing instruction set combination.Processor 1501 can also be one or more application specific processors, such as, dedicated
Integrated circuit (ASIC), honeycomb or baseband processor, field programmable gate array (FPGA), digital signal processor (DSP), net
It network processor, graphics processor, communication processor, encryption processor, coprocessor, embeded processor or is capable of handling
The logic of any other type of instruction.
Processor 1501 (it can be low power multi-core processor socket, such as ultralow voltage processor) may act as using
In the Main Processor Unit and central hub that are communicated with the various parts of the system.Implementable this processor is system on chip
(SoC).Processor 1501 is configured to execute the instruction for executing operation and step discussed in this article.System 1500 may be used also
Including the graphic interface communicated with optional graphics subsystem 1504, graphics subsystem 1504 may include display controller, figure
Processor and/or display device.
Processor 1501 can be communicated with memory 1503, and memory 1503 in one embodiment can be via multiple storages
Device device is implemented to provide the storage of the system of specified rate.Memory 1503 may include one or more volatile storages (or storage
Device) device, such as, random access memory (RAM), dynamic ram (DRAM), synchronous dram (SDRAM), static state RAM (SRAM)
Or other types of storage device.Memory 1503 can be stored including the finger by processor 1501 or the execution of any other device
Enable the information of sequence.For example, various operating systems, device driver, firmware (for example, input and output fundamental system or BIOS)
And/or the executable code and/or data of application can be loaded into memory 1503 and be executed by processor 1501.Operating system
It can be any kind of operating system, for example, robot operating system (ROS), coming fromCompanyOperating system, the Mac from Apple Inc.It comes fromCompany, LINUX, UNIX or it is other in real time or embedded OS.
System 1500 may also include I/O device, such as device 1505 to 1508, including Network Interface Unit 1505, optional
Input unit 1506 and other optional I/O devices 1507.Network Interface Unit 1505 may include wireless transceiver and/or net
Network interface card (NIC).The wireless transceiver can be WiFi transceiver, infrared transceiver, bluetooth transceiver, WiMax transmitting-receiving
Device, wireless cellular telephony transceiver, satellite transceiver (for example, global positioning system (GPS) transceiver) or other radio frequencies (RF)
Transceiver or their combination.NIC can be Ethernet card.
Input unit 1506 may include mouse, touch tablet, touch sensitive screen (it can be integrated with display device 1504),
Indicator device (such as, writing pencil) and/or keyboard are (for example, physical keyboard or a part display as touch sensitive screen is virtual
Keyboard).For example, input unit 1506 may include the touch screen controller for being connected to touch screen.Touch screen and touch screen controller
Any one of such as a variety of Touch technologies (including but not limited to capacitor, resistance, infrared and surface acoustic wave technique) can be used, with
And other proximity sensor arrays or other elements for the determining one or more points contacted with touch screen connect to detect it
Touching and mobile or interruption.
I/O device 1507 may include audio devices.Audio devices may include loudspeaker and/or microphone, to promote to support language
The function of sound, such as speech recognition, speech reproduction, digital record and/or telephony feature.Other I/O devices 1507 may also include logical
With the port universal serial bus (USB), parallel port, serial port, printer, network interface, bus bridge (for example, PCI-PCI bridge),
Sensor (for example, accelerometer motion sensor, gyroscope, magnetometer, optical sensor, compass, proximity sensor etc.)
Or their combination.Device 1507 may also include imaging subsystem (for example, video camera), the imaging subsystem
It may include the optical sensor for promoting camera function (such as, recording photograph and video clip), such as Charged Couple fills
Set (CCD) or complementary metal oxide semiconductor (CMOS) optical sensor.Certain sensors can be via sensor hub (not
Show) it is connected to interconnection piece 1510, and other devices of such as keyboard or heat sensor can be according to the concrete configuration of system 1500
Or design is controlled by embedded controller (not shown).
In order to provide the permanent storage to information such as data, application, one or more operating systems, large capacity is deposited
Storage device (not shown) can also be connected to processor 1501.In various embodiments, in order to realize thinner and lighter system
System responsiveness is designed and improves, this mass storage device can be implemented via solid-state device (SSD).However, at it
In its embodiment, mass storage device can mainly be implemented using hard disk drive (HDD), wherein small amount of SSD is deposited
Storage device serves as SSD cache to realize the non-volatile of context state and other this type of information during power cut-off incident
Storage, so that can be realized when the system activity is restarted quick power-on.In addition, flash memory device can be for example via serial
Peripheral interface (SPI) is connected to processor 1501.This flash memory device can provide the non-volatile memories of system software, the system
System software includes the BIOS and other firmwares of the system.
Storage device 1508 may include computer-accessible 1509 (also referred to as machine readable storage medium of storage medium
Or computer-readable medium), it is stored thereon with one or more for embodying any one or more of method or function as described herein
A instruction set or software (for example, module, unit and/or logic 1528).Processing module/unit/logic 1528 can indicate above-mentioned
Any of component, such as planning module 305, control module 306 etc..Processing module/unit/logic 1528 can also its by
Data processing system 1500, memory 1503 and processor 1501 completely or at least partially reside in memory during executing
In 1503 and/or in processor 1501, data processing system 1500, memory 1503 and processor 1501 also constitute machine and can visit
The storage medium asked.Processing module/unit/logic 1528 can also by network via Network Interface Unit 1505 carry out transmission or
It receives.
Computer readable storage medium 1509 can also be used to permanently store some software functions described above.Although
Computer readable storage medium 1509 is illustrated as single medium in the exemplary embodiment, but term is " computer-readable to deposit
Storage media " should be believed to comprise to store the single medium of one or more of instruction set or multiple media (for example, centralization
Or distributed data base and/or associated cache and server).Term " computer readable storage medium " should also be by
Think to include that can store or any medium of coded command collection, described instruction collection is used to be executed by machine and makes the machine
Any one or more of method of the device execution disclosure.Therefore, term " computer readable storage medium " should be believed to comprise
But it is not limited to solid-state memory and optical medium and magnetic medium or any other non-transitory machine readable media.
Process described herein module/unit/logic 1528, component and other feature are implementable for discrete hardware components
Or it is integrated in the function of hardware component (such as, ASICS, FPGA, DSP or similar device).In addition, processing module ,/unit/is patrolled
Collect 1528 implementable firmwares or functional circuit in hardware device.In addition, processing module/unit/logic 1528 can be with hard
Any combination of part device and software component is implemented.
It should be noted that although system 1500 is shown as the various parts with data processing system, it is not intended that table
Show any certain architectures or mode for making component connection;Because such details and embodiment of the present disclosure do not have substantial connection.
It should also be appreciated that have less component or may have more multipart network computer, handheld computer, mobile phone,
Server and/or other data processing systems can also be used together with embodiment of the present disclosure.
Some parts in foregoing detailed description according in computer storage to the algorithm of the operation of data bit
It indicates and presents with symbol.These algorithm descriptions and mode used in the technical staff that expression is in data processing field, with
Their work is substantially most effectively communicated to others skilled in the art.Herein, algorithm is typically considered
Lead to desired result is in harmony the sequence of operation certainly.These operations refer to the operation for needing that physical manipulation is carried out to physical quantity.
It should be borne in mind, however, that all these and similar terms be intended to register appropriate, and be only
Facilitate label applied to this tittle.Unless in other ways it is manifestly intended that otherwise it is to be appreciated that whole in described above
In a specification, refer to computer system using the discussion that term (term illustrated in such as the appended claims) carries out
Or the movement and processing of similar computing electronics, the computer system or computing electronics manipulate posting for computer system
The data of being expressed as in storage and memory physics (electronics) amount, and by the data be transformed into computer system memory or
Other data of physical quantity are similarly represented as in register or other this type of information storage devices, transmission or display device.
Embodiment of the present disclosure further relates to apparatuses for performing the operations herein.This computer program is stored
In non-transitory computer-readable medium.Machine readable media includes for the form readable with machine (for example, computer)
Store any mechanism of information.For example, machine readable (for example, computer-readable) medium include machine (for example, computer) can
Storage medium is read (for example, read-only memory (" ROM "), random access memory (" RAM "), magnetic disk storage medium, optical storage Jie
Matter, flash memory devices).
Discribed process or method can be executed by processing logic in aforementioned figures, and the processing logic includes hardware
The combination of (for example, circuit, special logic etc.), software (for example, being embodied in non-transitory computer-readable medium) or both.
Although the process or method are operated according to some sequences to describe, it will be understood that in the operation above
It is some to be executed in a different order.In addition, some operations can be performed in parallel rather than be sequentially performed.
Embodiment of the present disclosure is not described with reference to any specific programming language.It should be understood that can be used more
Programming language is planted to implement the introduction of embodiment of the present disclosure as described herein.
In above specification, by reference to the disclosure specific illustrative embodiment to embodiment of the present disclosure
It is described.It is evident that do not depart from the disclosure described in the appended claims it is broader spirit and
In the case where range, can to the present invention various modification can be adapted.Therefore, should come in descriptive sense rather than in restrictive sense
Understand the specification and drawings.
Claims (20)
1. a kind of for operating the method implemented by computer of automatic driving vehicle, comprising:
Based on sensing data obtained from multiple sensors, the driving ring around automatic driving vehicle is perceived by sensing module
Border generates perception information using multiple sensor models;
Based on from the received perception information of the sensing module, the rail of current drive cycle is used for by planning module planning
Mark;
Work as prelocalization according to the automatic driving vehicle, is based on the track, determines the pass around the automatic driving vehicle
Key area;
The automatic driving vehicle is controlled to be travelled according to the track;And
The metadata for describing the key area is transmitted to the sensing module via application programming interface, to allow
It states sensing module and generates the perception information for being used for next drive cycle according to the key area of the automatic driving vehicle.
2. according to the method described in claim 1, wherein, the key area around the automatic driving vehicle includes described
Automatic driving vehicle may potentially interfere with one or more regions of other traffic in next drive cycle.
3. according to the method described in claim 1, wherein, generating the perception information for being used for next drive cycle
When, which comprises
The first perception information for perceiving the key area is generated using the first sensor model in the sensor model;And
Remaining area of the perception other than the key area is generated using the second sensor model in the sensor model
Second perception information.
4. according to the method described in claim 3, wherein, first perception information is with more higher than second perception information
Resolution ratio describes driving environment, and wherein,
The sensing module consumes process resources more more than second perception information to generate first perception information.
5. being based on the rail according to the method described in claim 1, wherein, working as prelocalization according to the automatic driving vehicle
Mark determines that the key area around the automatic driving vehicle includes:
Work as prelocalization and the track based on the automatic driving vehicle, determines drive associated with the automatic driving vehicle
Sail scene;And
Search operation is executed in the database based on the Driving Scene, describes pass corresponding with the Driving Scene to obtain
The metadata in key area.
6. according to the method described in claim 5, further include:
Based on the metadata for describing the key area corresponding with the Driving Scene, according to the automatic Pilot vehicle
Construct the key area when prelocalization.
7. according to the method described in claim 5, further include:
Based on the metadata for describing the key area, determine limit around the automatic driving vehicle it is described crucially
The polygon in area;And
Shape based on the polygon calculates the vertex of the polygon, wherein the vertex of the polygon is for determining institute
State the size and positioning of key area.
8. according to the method described in claim 5, wherein, the database includes multiple data base entries, wherein each data
Specific Driving Scene is mapped to a group metadata by library entry, and the group metadata description, which limits, indicates the more of key area
The one or more rule of side shape.
9. a kind of non-transitory machine readable media for being stored with instruction, described instruction cause the place when executed by the processor
Reason device executes operation, and the operation includes:
Based on sensing data obtained from multiple sensors, the driving ring around automatic driving vehicle is perceived by sensing module
Border generates perception information using multiple sensor models;
Based on from the received perception information of the sensing module, the rail of current drive cycle is used for by planning module planning
Mark;
Work as prelocalization according to the automatic driving vehicle, is based on the track, determines the pass around the automatic driving vehicle
Key area;
The automatic driving vehicle is controlled to be travelled according to the track;And
The metadata for describing the key area is transmitted to the sensing module via application programming interface, to allow
It states sensing module and generates the perception information for being used for next drive cycle according to the key area of the automatic driving vehicle.
10. machine readable media according to claim 9, wherein around the automatic driving vehicle it is described crucially
Area includes one or more regions that the automatic driving vehicle may potentially interfere with other traffic in next drive cycle.
11. machine readable media according to claim 9, wherein generating for described in next drive cycle
When perception information, which comprises
The first perception information for perceiving the key area is generated using the first sensor model in the sensor model;And
Remaining area of the perception other than the key area is generated using the second sensor model in the sensor model
Second perception information.
12. machine readable media according to claim 11, wherein first perception information is than second perception
The higher resolution ratio of information describes driving environment, and wherein,
The sensing module consumes process resources more more than second perception information to generate first perception information.
13. machine readable media according to claim 9, wherein according to the prelocalization of working as of the automatic driving vehicle, base
In the track, determine that the key area around the automatic driving vehicle includes:
Work as prelocalization and the track based on the automatic driving vehicle, determines drive associated with the automatic driving vehicle
Sail scene;And
Search operation is executed in the database based on the Driving Scene, describes pass corresponding with the Driving Scene to obtain
The metadata in key area.
14. machine readable media according to claim 13, wherein the operation further include:
Based on the metadata for describing the key area corresponding with the Driving Scene, according to the automatic Pilot vehicle
Construct the key area when prelocalization.
15. machine readable media according to claim 13, wherein the operation further include:
Based on the metadata for describing the key area, determine limit around the automatic driving vehicle it is described crucially
The polygon in area;And
Shape based on the polygon calculates the vertex of the polygon, wherein the vertex of the polygon is for determining institute
State the size and positioning of key area.
16. machine readable media according to claim 13, wherein the database includes multiple data base entries,
In, specific Driving Scene is mapped to a group metadata by each data base entries, and the group metadata description is limited and indicated
The one or more rule of the polygon of key area.
17. a kind of data processing system, comprising:
Processor;And
Memory is attached to the processor;And
Sensing module and planning module, load execute in the memory and by the processor to execute operation, the behaviour
Work includes:
Based on sensing data obtained from multiple sensors, driving around automatic driving vehicle is perceived by the sensing module
Environment is sailed, generates perception information using multiple sensor models,
Based on from the received perception information of the sensing module, current drive cycle is used for by planning module planning
Track,
Work as prelocalization according to the automatic driving vehicle, is based on the track, determines the pass around the automatic driving vehicle
Key area,
The automatic driving vehicle is controlled to be travelled according to the track;And
The metadata for describing the key area is transmitted to the sensing module via application programming interface, to allow
It states sensing module and generates the perception information for being used for next drive cycle according to the key area of the automatic driving vehicle.
18. system according to claim 17, wherein the key area around the automatic driving vehicle includes institute
One or more regions of other traffic may be potentially interfered in next drive cycle by stating automatic driving vehicle.
19. system according to claim 17, wherein generating the perception information for being used for next drive cycle
When, which comprises
The first perception information for perceiving the key area is generated using the first sensor model in the sensor model;And
Remaining area of the perception other than the key area is generated using the second sensor model in the sensor model
Second perception information.
20. system according to claim 19, wherein first perception information is with higher than second perception information
Resolution ratio driving environment is described, and wherein,
The sensing module consumes process resources more more than second perception information to generate first perception information.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/944,289 | 2018-04-03 | ||
US15/944,289 US11378956B2 (en) | 2018-04-03 | 2018-04-03 | Perception and planning collaboration framework for autonomous driving |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110345955A true CN110345955A (en) | 2019-10-18 |
CN110345955B CN110345955B (en) | 2023-07-21 |
Family
ID=68054336
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910034390.7A Active CN110345955B (en) | 2018-04-03 | 2019-01-15 | Perception and planning collaboration framework for autopilot |
Country Status (3)
Country | Link |
---|---|
US (1) | US11378956B2 (en) |
JP (1) | JP6722312B2 (en) |
CN (1) | CN110345955B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113551662A (en) * | 2020-04-24 | 2021-10-26 | 深圳裹动科技有限公司 | Sensing method and dynamic sensing device applied to automatic driving vehicle and automatic driving vehicle |
CN113626545A (en) * | 2020-05-08 | 2021-11-09 | 大众汽车股份公司 | Vehicle, apparatus, method and computer program for determining a merged environment map |
WO2024066798A1 (en) * | 2022-09-27 | 2024-04-04 | 腾讯科技(深圳)有限公司 | Vehicle control method and apparatus, and device and storage medium |
Families Citing this family (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8977426B2 (en) | 2012-06-04 | 2015-03-10 | Geotab Inc. | VIN based accelerometer threshold |
US11130497B2 (en) | 2017-12-18 | 2021-09-28 | Plusai Limited | Method and system for ensemble vehicle control prediction in autonomous driving vehicles |
US11273836B2 (en) * | 2017-12-18 | 2022-03-15 | Plusai, Inc. | Method and system for human-like driving lane planning in autonomous driving vehicles |
US20190185012A1 (en) | 2017-12-18 | 2019-06-20 | PlusAI Corp | Method and system for personalized motion planning in autonomous driving vehicles |
US10782699B2 (en) * | 2018-03-10 | 2020-09-22 | Baidu Usa Llc | Real-time perception adjustment and driving adaption based on surrounding vehicles' behavior for autonomous driving vehicles |
US11548509B2 (en) | 2018-04-11 | 2023-01-10 | Hyundai Motor Company | Apparatus and method for controlling lane change in vehicle |
US11077854B2 (en) | 2018-04-11 | 2021-08-03 | Hyundai Motor Company | Apparatus for controlling lane change of vehicle, system having the same and method thereof |
US11334067B2 (en) | 2018-04-11 | 2022-05-17 | Hyundai Motor Company | Apparatus and method for providing safety strategy in vehicle |
EP3552902A1 (en) | 2018-04-11 | 2019-10-16 | Hyundai Motor Company | Apparatus and method for providing a driving path to a vehicle |
US11173910B2 (en) | 2018-04-11 | 2021-11-16 | Hyundai Motor Company | Lane change controller for vehicle system including the same, and method thereof |
EP3552901A3 (en) | 2018-04-11 | 2020-04-29 | Hyundai Motor Company | Apparatus and method for providing safety strategy in vehicle |
US11084491B2 (en) | 2018-04-11 | 2021-08-10 | Hyundai Motor Company | Apparatus and method for providing safety strategy in vehicle |
US10843710B2 (en) | 2018-04-11 | 2020-11-24 | Hyundai Motor Company | Apparatus and method for providing notification of control authority transition in vehicle |
US11351989B2 (en) | 2018-04-11 | 2022-06-07 | Hyundai Motor Company | Vehicle driving controller, system including the same, and method thereof |
EP3569460B1 (en) | 2018-04-11 | 2024-03-20 | Hyundai Motor Company | Apparatus and method for controlling driving in vehicle |
EP3552913B1 (en) * | 2018-04-11 | 2021-08-18 | Hyundai Motor Company | Apparatus and method for controlling to enable autonomous system in vehicle |
US11084490B2 (en) | 2018-04-11 | 2021-08-10 | Hyundai Motor Company | Apparatus and method for controlling drive of vehicle |
US11597403B2 (en) | 2018-04-11 | 2023-03-07 | Hyundai Motor Company | Apparatus for displaying driving state of vehicle, system including the same and method thereof |
US11602999B1 (en) * | 2018-05-01 | 2023-03-14 | Zoox, Inc. | Predictive control strategies for vehicles |
ES2736901A1 (en) | 2018-06-29 | 2020-01-08 | Geotab Inc | Characterization of a vehicle collision (Machine-translation by Google Translate, not legally binding) |
US11397089B2 (en) * | 2018-07-13 | 2022-07-26 | Uatc, Llc | Autonomous vehicle routing with route extension |
US11199847B2 (en) * | 2018-09-26 | 2021-12-14 | Baidu Usa Llc | Curvature corrected path sampling system for autonomous driving vehicles |
US11475576B2 (en) * | 2018-12-07 | 2022-10-18 | Thinkware Corporation | Method for detecting vehicle and device for executing the same |
US11161504B2 (en) * | 2019-03-19 | 2021-11-02 | Honda Motor Co., Ltd. | Vehicle control apparatus and method |
US11245909B2 (en) * | 2019-04-29 | 2022-02-08 | Baidu Usa Llc | Timestamp and metadata processing for video compression in autonomous driving vehicles |
US11180165B2 (en) * | 2019-12-26 | 2021-11-23 | Baidu Usa Llc | Autonomous driving vehicle three-point turn |
WO2021128287A1 (en) * | 2019-12-27 | 2021-07-01 | 华为技术有限公司 | Data generation method and device |
US11941986B2 (en) | 2021-02-03 | 2024-03-26 | Geotab Inc. | Methods for characterizing a low-impact vehicle collision using high-rate acceleration data |
US11862022B2 (en) | 2021-02-03 | 2024-01-02 | Geotab Inc. | Methods for characterizing a vehicle collision |
US11884285B2 (en) | 2021-02-03 | 2024-01-30 | Geotab Inc. | Systems for characterizing a vehicle collision |
CN113406955B (en) * | 2021-05-10 | 2022-06-21 | 江苏大学 | Complex network-based automatic driving automobile complex environment model, cognitive system and cognitive method |
CN115691099A (en) * | 2021-07-30 | 2023-02-03 | 华为技术有限公司 | Sensing capability information generation method, using method and device |
US20230065284A1 (en) * | 2021-09-01 | 2023-03-02 | Baidu Usa Llc | Control and planning with localization uncertainty |
US11845454B2 (en) | 2021-09-14 | 2023-12-19 | Motional Ad Llc | Operational envelope detection with situational assessment |
US11851091B2 (en) | 2021-09-14 | 2023-12-26 | Motional Ad Llc | Immobility detection within situational context |
US20230093601A1 (en) * | 2021-09-14 | 2023-03-23 | Motional Ad Llc | Environmental limitation and sensor anomaly system and method |
CN114428501B (en) * | 2021-12-17 | 2024-06-21 | 重庆特斯联智慧科技股份有限公司 | Old man home service robot and control method thereof |
US20230303092A1 (en) * | 2022-03-28 | 2023-09-28 | Gm Cruise Holdings Llc | Perception error identification |
CN115056784B (en) * | 2022-07-04 | 2023-12-05 | 小米汽车科技有限公司 | Vehicle control method, device, vehicle, storage medium and chip |
US20240131984A1 (en) * | 2022-10-20 | 2024-04-25 | Motional Ad Llc | Turn signal assignment for complex maneuvers |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1834686A (en) * | 2005-03-17 | 2006-09-20 | 三洋电机株式会社 | Detection device |
CN104943684A (en) * | 2014-03-31 | 2015-09-30 | 比亚迪股份有限公司 | Pilotless automobile control system and automobile with same |
DE102015205133A1 (en) * | 2015-03-20 | 2016-09-22 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for determining a movement planning for an at least partially automated driving of a vehicle |
CN106871915A (en) * | 2015-12-04 | 2017-06-20 | 大众汽车有限公司 | It is used for the method and apparatus of automatic Pilot in a motor vehicle |
US20170314954A1 (en) * | 2016-05-02 | 2017-11-02 | Google Inc. | Systems and Methods for Using Real-Time Imagery in Navigation |
WO2018014916A1 (en) * | 2016-07-22 | 2018-01-25 | Conti Temic Microelectronic Gmbh | Camera device and method for detecting a surrounding area of a driver's own vehicle |
WO2018014917A1 (en) * | 2016-07-22 | 2018-01-25 | Conti Temic Microelectronic Gmbh | Camera device for capturing a surrounding area of a driver's own vehicle and method for providing a driver assistance function |
Family Cites Families (40)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19536512A1 (en) * | 1995-09-29 | 1997-04-03 | Bayerische Motoren Werke Ag | Gear change control for automatic transmissions in motor vehicles with an electronic control unit |
US7392118B2 (en) * | 2003-08-18 | 2008-06-24 | Fico Mirrors, Sa | System and method for monitoring the external environment of a motor vehicle |
JP4980076B2 (en) * | 2007-01-11 | 2012-07-18 | 富士重工業株式会社 | Vehicle driving support device |
JP5115792B2 (en) * | 2007-07-04 | 2013-01-09 | オムロン株式会社 | Image processing apparatus and method, and program |
JP5600330B2 (en) * | 2012-02-16 | 2014-10-01 | 富士重工業株式会社 | Vehicle driving support device |
GB201219742D0 (en) * | 2012-11-02 | 2012-12-12 | Tom Tom Int Bv | Methods and systems for generating a horizon for use in an advanced driver assistance system (adas) |
DE102013013867A1 (en) * | 2013-08-20 | 2015-03-12 | Audi Ag | Motor vehicle and method for controlling a motor vehicle |
US10422649B2 (en) * | 2014-02-24 | 2019-09-24 | Ford Global Technologies, Llc | Autonomous driving sensing system and method |
EP3855276A1 (en) * | 2014-09-05 | 2021-07-28 | SZ DJI Technology Co., Ltd. | Multi-sensor environmental mapping |
US9493157B2 (en) * | 2015-01-29 | 2016-11-15 | Toyota Motor Engineering & Manufacturing North America, Inc. | Autonomous vehicle operation in obstructed occupant view and sensor detection environments |
US9779312B2 (en) * | 2015-01-30 | 2017-10-03 | Honda Motor Co., Ltd. | Environment recognition system |
KR102623680B1 (en) * | 2015-02-10 | 2024-01-12 | 모빌아이 비젼 테크놀로지스 엘티디. | Sparse map for autonomous vehicle navigation |
US10152882B2 (en) * | 2015-11-30 | 2018-12-11 | Nissan North America, Inc. | Host vehicle operation using remote vehicle intention prediction |
JP6561819B2 (en) | 2015-12-15 | 2019-08-21 | 株式会社デンソー | Communication control device |
US20190143972A1 (en) * | 2016-03-15 | 2019-05-16 | Honda Motor Co., Ltd. | Vehicle control system, vehicle control method, and vehicle control program |
CN105751230B (en) * | 2016-03-31 | 2018-12-21 | 纳恩博(北京)科技有限公司 | A kind of controlling of path thereof, paths planning method, the first equipment and the second equipment |
US10317900B2 (en) * | 2016-05-13 | 2019-06-11 | GM Global Technology Operations LLC | Controlling autonomous-vehicle functions and output based on occupant position and attention |
KR101851155B1 (en) * | 2016-10-12 | 2018-06-04 | 현대자동차주식회사 | Autonomous driving control apparatus, vehicle having the same and method for controlling the same |
DE102016223579A1 (en) * | 2016-11-28 | 2018-05-30 | Robert Bosch Gmbh | Method for determining data of a traffic situation |
TWI611280B (en) * | 2016-12-12 | 2018-01-11 | 財團法人工業技術研究院 | Tele-operated vehicle, and vehicle control device and control method thereof |
US10422639B2 (en) * | 2016-12-30 | 2019-09-24 | DeepMap Inc. | Enrichment of point cloud data for high-definition maps for autonomous vehicles |
KR102254079B1 (en) * | 2017-01-04 | 2021-05-20 | 현대자동차주식회사 | Vehicle And Control Method Thereof |
US10445928B2 (en) * | 2017-02-11 | 2019-10-15 | Vayavision Ltd. | Method and system for generating multidimensional maps of a scene using a plurality of sensors of various types |
US10281920B2 (en) * | 2017-03-07 | 2019-05-07 | nuTonomy Inc. | Planning for unknown objects by an autonomous vehicle |
WO2018176000A1 (en) * | 2017-03-23 | 2018-09-27 | DeepScale, Inc. | Data synthesis for autonomous control systems |
JP6450413B2 (en) | 2017-03-31 | 2019-01-09 | 本田技研工業株式会社 | Vehicle control device |
US10453351B2 (en) * | 2017-07-17 | 2019-10-22 | Aurora Flight Sciences Corporation | System and method for detecting obstacles in aerial systems |
JP7009834B2 (en) * | 2017-08-23 | 2022-01-26 | 株式会社デンソー | Collection system and center |
US10866588B2 (en) * | 2017-10-16 | 2020-12-15 | Toyota Research Institute, Inc. | System and method for leveraging end-to-end driving models for improving driving task modules |
WO2019079211A1 (en) * | 2017-10-19 | 2019-04-25 | DeepMap Inc. | Lidar to camera calibration for generating high definition maps |
EP3477333B1 (en) * | 2017-10-26 | 2023-08-09 | Continental Autonomous Mobility Germany GmbH | Method and device of determining kinematics of a target |
US11163309B2 (en) * | 2017-11-30 | 2021-11-02 | Direct Current Capital LLC | Method for autonomous navigation |
WO2019133743A1 (en) * | 2017-12-27 | 2019-07-04 | Drive.Ai Inc | Method for accessing supplemental perception data from other vehicles |
US20190204834A1 (en) * | 2018-01-04 | 2019-07-04 | Metawave Corporation | Method and apparatus for object detection using convolutional neural network systems |
US10860020B2 (en) * | 2018-01-23 | 2020-12-08 | Toyota Research Institute, Inc. | System and method for adaptive perception in a vehicle |
US10976745B2 (en) * | 2018-02-09 | 2021-04-13 | GM Global Technology Operations LLC | Systems and methods for autonomous vehicle path follower correction |
KR102420568B1 (en) * | 2018-04-27 | 2022-07-13 | 삼성전자주식회사 | Method for determining a position of a vehicle and vehicle thereof |
EP3803828B1 (en) * | 2018-05-31 | 2022-03-30 | Nissan North America, Inc. | Probabilistic object tracking and prediction framework |
US10699167B1 (en) * | 2018-10-19 | 2020-06-30 | Waymo Llc | Perception visualization tool |
US11153721B2 (en) * | 2018-12-27 | 2021-10-19 | Intel Corporation | Sensor network enhancement mechanisms |
-
2018
- 2018-04-03 US US15/944,289 patent/US11378956B2/en active Active
-
2019
- 2019-01-15 CN CN201910034390.7A patent/CN110345955B/en active Active
- 2019-02-04 JP JP2019017849A patent/JP6722312B2/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1834686A (en) * | 2005-03-17 | 2006-09-20 | 三洋电机株式会社 | Detection device |
CN104943684A (en) * | 2014-03-31 | 2015-09-30 | 比亚迪股份有限公司 | Pilotless automobile control system and automobile with same |
DE102015205133A1 (en) * | 2015-03-20 | 2016-09-22 | Bayerische Motoren Werke Aktiengesellschaft | Method and device for determining a movement planning for an at least partially automated driving of a vehicle |
CN106871915A (en) * | 2015-12-04 | 2017-06-20 | 大众汽车有限公司 | It is used for the method and apparatus of automatic Pilot in a motor vehicle |
US20170314954A1 (en) * | 2016-05-02 | 2017-11-02 | Google Inc. | Systems and Methods for Using Real-Time Imagery in Navigation |
WO2018014916A1 (en) * | 2016-07-22 | 2018-01-25 | Conti Temic Microelectronic Gmbh | Camera device and method for detecting a surrounding area of a driver's own vehicle |
WO2018014917A1 (en) * | 2016-07-22 | 2018-01-25 | Conti Temic Microelectronic Gmbh | Camera device for capturing a surrounding area of a driver's own vehicle and method for providing a driver assistance function |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113551662A (en) * | 2020-04-24 | 2021-10-26 | 深圳裹动科技有限公司 | Sensing method and dynamic sensing device applied to automatic driving vehicle and automatic driving vehicle |
CN113626545A (en) * | 2020-05-08 | 2021-11-09 | 大众汽车股份公司 | Vehicle, apparatus, method and computer program for determining a merged environment map |
WO2024066798A1 (en) * | 2022-09-27 | 2024-04-04 | 腾讯科技(深圳)有限公司 | Vehicle control method and apparatus, and device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
US11378956B2 (en) | 2022-07-05 |
US20190302768A1 (en) | 2019-10-03 |
JP6722312B2 (en) | 2020-07-15 |
CN110345955B (en) | 2023-07-21 |
JP2019182399A (en) | 2019-10-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110345955A (en) | Perception and planning cooperation frame for automatic Pilot | |
CN110388931A (en) | The two-dimentional bounding box of object is converted into the method for the three-dimensional position of automatic driving vehicle | |
JP6644742B2 (en) | Algorithms and infrastructure for robust and efficient vehicle positioning | |
CN110239562A (en) | The real-time perception adjustment based on surrounding vehicles behavior of automatic driving vehicle is adjusted with driving | |
CN110377024A (en) | Automaticdata for automatic driving vehicle marks | |
CN109489673A (en) | Data-driven map updating system for automatic driving vehicle | |
CN110386142A (en) | Pitch angle calibration method for automatic driving vehicle | |
CN110377025A (en) | Sensor aggregation framework for automatic driving vehicle | |
CN109947090A (en) | Non- chocking limit for automatic driving vehicle planning | |
CN110389583A (en) | The method for generating the track of automatic driving vehicle | |
CN108981730A (en) | For generating the method and system of reference path for operation automatic driving vehicle | |
CN108387241A (en) | Update the method and system of the positioning map of automatic driving vehicle | |
CN110389584A (en) | Method for assessing the track candidate item of automatic driving vehicle | |
CN109935077A (en) | System for constructing vehicle and cloud real-time traffic map for automatic driving vehicle | |
CN110096053A (en) | Driving locus generation method, system and machine readable media for automatic driving vehicle | |
CN110389580A (en) | Method for planning the drift correction in the path of automatic driving vehicle | |
CN110325935A (en) | The lane guide line based on Driving Scene of path planning for automatic driving vehicle | |
CN110378483A (en) | The system and method for training machine learning model being deployed on analog platform | |
CN109429518A (en) | Automatic Pilot traffic forecast based on map image | |
CN110119140A (en) | System and method for acceleration curve projection | |
CN110389585A (en) | The speed planning device based on study for automatic driving vehicle | |
CN110462543A (en) | The method based on emulation that perception for assessing automatic driving vehicle requires | |
CN108732589A (en) | The training data of Object identifying is used for using 3D LIDAR and positioning automatic collection | |
CN110083149A (en) | For infeed mechanism after the path of automatic driving vehicle and speed-optimization | |
CN108604095A (en) | The method of the steering rate of dynamic adjustment automatic driving vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |